Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM.

翻译：随着计算机视觉技术在实际应用中的快速普及，面向机器的图像编码（ICM）日益重要。然而，大多数基于神经网络的ICM框架只能在固定码率下运行，因此需要针对每个目标码率进行单独训练。这一限制可能阻碍其实际应用。现有的可变码率图像压缩方法虽能缓解此问题，但通常依赖额外的训练，从而增加计算成本并使得部署复杂化。此外，可变码率控制在ICM领域尚未得到充分探索。为解决这些挑战，我们提出了一种无需训练的量化强度控制框架，可实现灵活的码率调整。该方法通过利用超先验网络预测的尺度参数，在通道和空间维度上自适应地调制量化步长。这使得模型能够在粗略量化次要区域的同时，保留语义上重要的区域。我们的架构设计进一步实现了通过单一参数进行连续码率控制。实验结果表明，所提方法具有显著效果，相比非自适应的可变码率基线，最高可节省11.07%的BD-rate。代码已发布于 https://github.com/qwert-top/AQVR-ICM。